Object Detection and Pose Estimation Using Deep

**Flanders Make**:
Flanders Make is the strategic research centre for the manufacturing industry. Our mission is to strengthen the long-term international competitiveness of the Flemish manufacturing industry. That’s why we work together with SMEs and large companies on pre-competitive, industry-driven technological research, resulting in concrete product and production innovation in the vehicle industry, the manufacturing industry, and production environments.

**Goal of the internship**:
The goal of this internship and thesis is to design, build and integrate an additional (fifth) industrial machine emulator on the Flanders Make DC network. This emulator shall be based on a Schneider drive, together with a WEG induction machine. The assembly shall be rated for 3 kW of mechanical power at 1450 rpm.

This workload can be divided in following successive steps:

- Introduction to the project, prototype and existing emulators
- Requirements analysis
- Hardware analysis and design of the emulator (CAD)
- Ordering of the components
- Building, commissioning of the drive and integration in the DC prototype
- Software integration (control, communication and HMI)
- Testing, demonstration and documentation

The design (hardware and electrical) phase will see the use of CAD software. The software integration of the drive happens in the TwinCAT (Beckhoff) environment, over an EtherCAT or Profinet network. The construction of an HMI for testing and demonstration will be done in MATLAB / Simulink. Moreover, the previously cited framework can be used for simulation and learnings.

The learning targets are:

- Introduction to the full design and execution of a laboratory prototype
- Inclusion in a research project, with a practical outcome and publication of technical documentation
- Introduction to the TwinCAT environment
- Development tasks in CAD software and MATLAB / Simulink (RT)

While Flanders Make stresses the importance of independency, the intern will get all the necessary support from its colleagues and partners to properly reach the objectives, the most important of them remaining learning and practicing research engineering.

**Profile Student**:

- Bachelor degree in electrical engineering, computer science, or mechatronics;
- Knowledge of image processing, computer vision, machine learning is highly recommended;
- Good programming skills in Python or C++;
- Experience in open-source deep learning frameworks such as TensorFlow or PyTorch is a plus;
- Result oriented, responsible and proactive;
- A good communicator, able to communicate in English;
- Eager to learn and a team player.
- Only EEA or Swiss nationals can be accepted for internships due to work permit regulations._

**Practical Data**:
This assignment is an internship but can also be executed by a thesis student from a Belgian university.

The assignment is for min 4 month to maximum 6 months and takes place at the offices of Flanders Make offices located in Leuven, Belgium.

For internships:
all software and hardware needed for the execution of the project will be provided by Flanders Make.